© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82790
    Prev
    Next
    INDEX
    Explanations

    variations of the word "capture."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    636
    -0.08
    pton
    -0.07
    .Void
    -0.06
    NT
    -0.06
    oi
    -0.06
    hop
    -0.06
    igi
    -0.06
    uve
    -0.06
    051
    -0.06
    bucks
    -0.06
    POSITIVE LOGITS
    icum
    0.08
     cap
    0.08
    ury
    0.07
    uring
    0.07
     khẩu
    0.07
    (cap
    0.07
    cap
    0.07
    stone
    0.07
    ura
    0.07
    oral
    0.07
    Activations Density 0.005%

    No Known Activations